A mechanical simulation analysis method for heavy-loaded gear structures

Abstract

The present invention relates to the technical field of mechanical simulation analysis, and in particular to a mechanical simulation analysis method for a heavy-loaded gear structure. The method comprises the following steps: establishing a heavy-loaded gear physical model through basic parameters of the heavy-loaded gear structure; analyzing the geometric unit data of the heavy-loaded gear structure according to the heavy-loaded gear physical model; performing heavy-loaded gear operation simulation working condition analysis on the heavy-loaded gear physical model through simulation parameters of heterogeneous operation conditions of engineering machinery, and generating heavy-loaded gear operation simulation working condition data; performing local unit nonlinear stress characteristic analysis of heavy-loaded gear operation based on the heavy-loaded gear operation simulation working condition data and the heavy-loaded gear structure geometric unit data, and generating heavy-loaded gear operation local unit nonlinear stress characteristic data; analyzing heterogeneous operation condition gear simulation mechanical data according to the heavy-loaded gear operation local unit nonlinear stress characteristic data. The present invention realizes accurate heavy-loaded gear stress analysis through mechanical simulation of heavy-loaded gears.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical simulation analysis, and in particular to a mechanical simulation analysis method for a heavy-loaded gear structure. Background Art

[0002] In modern engineering machinery, gear systems, as key transmission components, are widely used in a variety of heavy-duty and high-load mechanical equipment. Heavy-duty gears, in particular, are subject to enormous loads and complex operating environments. With the continuous development of engineering machinery, gear system design requirements are becoming increasingly stringent. They must not only maintain stable operating performance over a long service life but also exhibit strong fatigue and wear resistance. Gear mechanical analysis has become an important research direction in gear engineering, enabling accurate performance prediction, early identification of potential failure modes, and effective optimization of heavy-duty gear designs. Mechanical simulation analysis methods for heavy-duty gear structures, based on mechanical simulation technology, establish a three-dimensional model of the gear structure and conduct a comprehensive analysis of the stress characteristics of heavy-duty gears under different operating conditions. These methods simulate the gear's operating state under heavy loads and assess its mechanical properties and potential failure risks. However, existing mechanical simulation analysis methods for heavy-duty gear structures rely primarily on theoretical calculations and empirical formulas, lacking a comprehensive understanding of the mechanical simulation of gears under complex operating conditions, particularly in-depth analysis of the nonlinear stresses, structural losses, and dynamic failure characteristics of gears under actual operating conditions. Summary of the Invention

[0003] Based on this, the present invention provides a mechanical simulation analysis method for a heavy-duty gear structure to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a mechanical simulation analysis method for a heavy-loaded gear structure includes the following steps:

[0005] Step S1: obtaining basic structural parameters of heavy-duty gears of engineering machinery; performing digital modeling of the physical structure of the heavy-duty gears based on the basic structural parameters of the heavy-duty gears to generate a physical model of the heavy-duty gears;

[0006] Step S2: dividing each structural geometric unit of the heavy-duty gear according to the heavy-duty gear physical model to generate the structural geometric unit data of the heavy-duty gear;

[0007] Step S3: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the heavy-loaded gear physical model and the geometric unit data of the heavy-loaded gear structure, generating nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation; and performing a mechanical simulation feedback operation of the heavy-loaded gear structure based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation;

[0008] Step S4: performing a structural loss trend characteristic analysis of the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation to generate heavy-loaded gear operation structural loss trend characteristic data; performing a structural loss anomaly analysis of the heavy-loaded gear operation based on the structural loss trend characteristic data of the heavy-loaded gear operation to generate heavy-loaded gear structural loss anomaly data;

[0009] Step S5: performing a heavy-duty gear structural loss disturbance dynamic failure characteristic analysis based on the heavy-duty gear operating structure loss trend characteristic data to generate the heavy-duty gear structural loss disturbance dynamic failure characteristic data; performing a heavy-duty gear structural loss disturbance abnormality analysis based on the heavy-duty gear structural loss disturbance dynamic failure characteristic data to generate the heavy-duty gear structural loss disturbance abnormality data;

[0010] Step S6: Perform heavy-loaded gear structure abnormality analysis based on the heavy-loaded gear structure loss abnormality data or the heavy-loaded gear structure loss disturbance abnormality data to generate heavy-loaded gear structure abnormality data; perform heavy-loaded gear structure optimization design feedback operation through the heavy-loaded gear structure abnormality data.

[0011] Furthermore, step S1 includes the following steps:

[0012] Step S11: acquiring basic structural parameters of heavy-duty gears of engineering machinery, wherein the basic structural parameters of heavy-duty gears include material characteristic parameters of heavy-duty gears and geometric structure design parameters of heavy-duty gears;

[0013] Step S12: performing three-dimensional modeling of the heavy-duty gear geometric structure according to the heavy-duty gear geometric structure design parameters to generate a three-dimensional model of the heavy-duty gear geometric structure;

[0014] Step S13: performing numerical processing on the strength of the heavy-duty gear material characteristics according to the heavy-duty gear material characteristic parameters to generate numerical heavy-duty gear material characteristic data;

[0015] Step S14: performing digital modeling of the physical structure of the heavy-duty gear using the three-dimensional model of the heavy-duty gear geometric structure and the corresponding digitized heavy-duty gear material characteristic data to generate a heavy-duty gear physical model.

[0016] Furthermore, step S2 includes the following steps:

[0017] Step S21: performing a structural area division process on the heavy-duty gear according to the heavy-duty gear physical model to generate a structural area heavy-duty gear physical model;

[0018] Step S22: performing stress-specific analysis on each structural region of the structural region heavy-duty gear physical model to generate stress-specific data of the structural region heavy-duty gear;

[0019] Step S23: using the structural region heavy-duty gear stress-specific data, the structural region heavy-duty gear physical model is divided into various structural geometric units of the heavy-duty gear to generate the heavy-duty gear structural geometric unit data.

[0020] Furthermore, step S3 includes the following steps:

[0021] Step S31: obtaining simulation parameters of heterogeneous operation conditions of construction machinery;

[0022] Step S32: performing heavy-load gear operation simulation analysis on the heavy-load gear physical model using the engineering machinery heterogeneous operation condition simulation parameters to generate heavy-load gear operation simulation condition data;

[0023] Step S33: analyzing the heavy-loaded gear operation stress influencing factors based on the heavy-loaded gear operation simulation condition data to generate the heavy-loaded gear operation stress influencing factors, wherein the heavy-loaded gear operation stress influencing factors include the operation load fluctuation influencing factors, the gear speed influencing factors, and the gear force influencing factors;

[0024] Step S34: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the stress influencing factor of the heavy-loaded gear operation and the geometric unit data of the heavy-loaded gear structure, and generating nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation;

[0025] Step S35: Perform gear simulation mechanical analysis of heterogeneous operating conditions based on the nonlinear stress characteristic data of the local unit of heavy-duty gear operation corresponding to the simulation parameters of the heterogeneous operating conditions of the engineering machinery, and generate gear simulation mechanical data of the heterogeneous operating conditions; perform mechanical simulation feedback operations of the heavy-duty gear structure through the gear simulation mechanical data of the heterogeneous operating conditions.

[0026] Furthermore, step S34 includes the following steps:

[0027] Step S341: performing an analysis of the correlation characteristics between the operating load and the gear speed based on the operating load fluctuation influencing factor and the gear speed influencing factor, and generating operating load-gear speed correlation characteristic data;

[0028] Step S342: performing a heavy-duty gear simulated force numerical transmission benefit analysis on the gear force influencing factors based on the operating load-gear speed correlation characteristic data, and generating heavy-duty gear simulated force numerical transmission benefit data;

[0029] Step S343: performing a heavy-duty gear structure geometric unit spatial feature analysis based on the heavy-duty gear structure geometric unit data to generate heavy-duty gear structure geometric unit spatial feature data;

[0030] Step S344: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the numerical transmission benefit data of the simulated force of the heavy-loaded gear and the spatial characteristic data of the geometric unit of the heavy-loaded gear structure, and generating the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation.

[0031] Furthermore, step S4 includes the following steps:

[0032] Step S41: performing a structural loss assessment process for the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation to generate structural loss assessment data for the heavy-loaded gear operation;

[0033] Step S42: performing a stress trend analysis of the local unit of the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation, and generating stress trend data of the local unit of the heavy-loaded gear operation;

[0034] Step S43: performing a structural loss trend characteristic analysis of the heavy-loaded gear operation on the heavy-loaded gear operation structural loss assessment data based on the heavy-loaded gear operation local unit stress trend data, and generating heavy-loaded gear operation structural loss trend characteristic data;

[0035] Step S44: performing heavy-loaded gear structural loss anomaly analysis based on the heavy-loaded gear operation structural loss trend characteristic data to generate heavy-loaded gear structural loss anomaly data.

[0036] Furthermore, step S42 includes the following steps:

[0037] The time series data analysis of the local unit nonlinear stress characteristic data of the heavy-loaded gear operation is performed to generate the time series local unit nonlinear stress characteristic data; the local unit stress trend analysis of the heavy-loaded gear operation is performed on the time series local unit nonlinear stress characteristic data using the preset long short-term memory neural network algorithm to generate the local unit stress trend data of the heavy-loaded gear operation.

[0038] Furthermore, step S43 includes the following steps:

[0039] Based on the local unit stress trend data of heavy-loaded gear operation, the heavy-loaded gear operation structural loss assessment data is recursively analyzed to generate recursive heavy-loaded gear operation structural loss data; based on the recursive heavy-loaded gear operation structural loss data, the structural loss trend characteristic analysis of heavy-loaded gear operation is performed to generate heavy-loaded gear operation structural loss trend characteristic data.

[0040] Furthermore, step S5 includes the following steps:

[0041] Step S51: mapping the heavy-loaded gear operation structure loss trend characteristic data to the heavy-loaded gear operation simulation condition data to perform loss disturbance topology data identification, and generate heavy-loaded gear operation loss disturbance topology data;

[0042] Step S52: Acquire historical heavy-duty gear failure operation evaluation data, and design a heavy-duty gear failure operation intelligent evaluation engine based on the historical heavy-duty gear failure operation evaluation data;

[0043] Step S53: performing a heavy-duty gear failure characteristic analysis on the heavy-duty gear operation loss disturbance topology data by using the heavy-duty gear failure operation intelligent evaluation engine to generate the heavy-duty gear failure characteristic data.

[0044] Step S54: performing heavy-loaded gear structure loss disturbance anomaly analysis based on the loss disturbance heavy-loaded gear dynamic failure characteristic data to generate heavy-loaded gear structure loss disturbance anomaly data.

[0045] The beneficial effects of this application lie in obtaining basic structural parameters of heavy-duty gears for construction machinery and completing digital modeling of the heavy-duty gear's physical structure based on these parameters, achieving efficient conversion from basic data to digital models. The obtained material property parameters and geometric design parameters of the heavy-duty gear enable the model to fully reflect the physical properties and actual structural characteristics of the gear. Through three-dimensional geometric modeling and numerical strength processing of material properties, the generated heavy-duty gear physical model more accurately reflects the actual performance of the gear. This not only provides high-quality basic data support for subsequent simulation analysis, but also effectively improves the accuracy and efficiency of the gear design and analysis process, thereby meeting the high requirements of complex construction machinery operating conditions. The structural region division and geometric unit division of the heavy-duty gear physical model enable fine-grained modeling of the gear structure. In particular, the combination of stress-specific data generated by stress-specific analysis enables the division process to more accurately reflect the stress distribution characteristics of different regions. This improves the accuracy of nonlinear stress analysis and reduces errors caused by improper region division in traditional modeling. By introducing simulation parameters for heterogeneous construction machinery operating conditions and combining them with the heavy-duty gear physical model, the entire process of operating simulation analysis and local unit nonlinear stress characteristic analysis is completed. Accurately modeling stress-influencing factors, such as operating load fluctuation factors, gear speed factors, and gear force factors, effectively captures the key mechanical characteristics of heavy-loaded gears under different operating conditions. Furthermore, by correlating characteristic data of operating load and gear speed, and comprehensively analyzing the numerical transfer efficiency of simulated forces and the spatial characteristics of geometric units, the generated local unit nonlinear stress characteristic data is highly granular and accurate. This multi-dimensional, multi-level analysis approach improves the interpretability of gear operating characteristics. Gear simulation mechanical analysis based on heterogeneous operating condition simulation parameters deeply investigates the mechanical behavior of heavy-loaded gears under complex operating conditions, accurately reflecting the mechanical response characteristics of gears under different operating conditions. This provides high-quality data support for design optimization and structural improvement, effectively enhancing the intelligence of gear mechanical simulation analysis. Structural loss assessment and trend analysis based on local unit nonlinear stress characteristic data accurately captures the structural loss patterns of heavy-loaded gears during long-term operation. Using a long short-term memory (LSTM) neural network algorithm, the temporal variations of stress characteristics are effectively analyzed, generating local unit stress trend data. Further recursive loss analysis is performed to generate highly accurate structural loss trend characteristic data. This approach overcomes the limited time series data processing capabilities of traditional loss analysis and significantly improves the accuracy of loss prediction under complex operating conditions. Loss anomaly analysis based on trend feature data rapidly identifies potential anomalies, providing a scientific basis for gear maintenance and fault warnings, and reducing the risk of sudden failures during operation. By combining structural loss trend feature data with operational simulation data, topological data identification enables analysis of the spatial distribution characteristics of loss disturbances.An intelligent assessment engine designed with historical failure assessment data accurately captures dynamic failure characteristics during gear operation, enabling prediction of dynamic failure behavior based on disturbance signatures. This process not only enhances understanding of the impact of loss disturbances but also, through intelligent assessment algorithms, improves the efficiency and accuracy of dynamic failure signature analysis. Anomaly analysis of dynamic failure signature data can reveal potential weaknesses in the gear structure, providing crucial support for life prediction and design optimization of key components, thereby comprehensively improving gear operational reliability. Comprehensive gear structural anomaly analysis was conducted based on structural loss anomaly data and structural loss disturbance anomaly data. The generated structural anomaly data provides precise guidance for subsequent design optimization. By integrating anomaly signatures from multiple data sources, this approach can deeply explore the failure mechanisms and design flaws of heavily loaded gears under extreme operating conditions. The generated anomaly data is then used to execute optimization design feedback, achieving a closed-loop optimization process from anomaly detection to design improvement, ensuring high reliability and long life of the gear structure under complex operating conditions.

[0046] Therefore, the mechanical simulation analysis method for heavy-loaded gear structures of the present invention obtains simulation parameters for the heterogeneous operating conditions of engineering machinery to accurately analyze the gear's operating conditions. This method can more comprehensively reflect the actual performance of gears under complex operating conditions, particularly the impact of load fluctuations, gear speed changes, and other factors on gear performance. By dividing the gear's structural geometric units and analyzing the nonlinear stress characteristics of these local units based on operating condition data—that is, the gear operating stress characteristics of different structural units under different operating conditions—the method accurately predicts the nonlinear stresses and fatigue damage that occur during gear operation. This avoids neglecting the complex stress states of heavy-loaded gear operation, identifies potential gear loss issues in advance, and analyzes the direct effects of mechanical forces on gear failure. By introducing the identification of gear loss perturbation topological data and analyzing dynamic failure characteristics, failure modes can be identified during gear operation. By analyzing the potential effects of failure conditions on gear failure under the mechanical forces of gear operation, the gear structure can be further optimized with greater precision. This ensures a comprehensive understanding of mechanical simulation analysis of gears under complex operating conditions and provides in-depth analysis of the nonlinear stresses, structural losses, and dynamic failure characteristics of gears under actual operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic flow chart of the steps of an intelligent medication management method of the present invention;

[0048] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0049] Figure 3 for Figure 1Detailed implementation steps of step S4 in FIG.

[0050] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0051] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0052] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0053] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0054] To achieve this, please refer to Figures 1 to 3 The present invention provides a mechanical simulation analysis method for a heavy-duty gear structure, comprising the following steps:

[0055] Step S1: obtaining basic structural parameters of heavy-duty gears of engineering machinery; performing digital modeling of the physical structure of the heavy-duty gears based on the basic structural parameters of the heavy-duty gears to generate a physical model of the heavy-duty gears;

[0056] In an embodiment of the present invention, basic parameters of a heavy-duty gear structure, including material property parameters and geometric design parameters, are obtained using pre-input engineering machinery design data. Material property parameters include density, elastic modulus, Poisson's ratio, tensile strength, and yield strength. Mechanical property testing of samples is performed using test methods specified in ASTM international standards to obtain numerical material property data. Geometric design parameters include the number of gear teeth, module, tooth width, pressure angle, helix angle, and other parameters. Parameter values are directly extracted from design drawings or computer-aided design (CAD) files to ensure the accuracy and consistency of the parameter sources. Based on the heavy-duty gear geometric design parameters, 3D modeling of the heavy-duty gear geometry is performed using 3D modeling software (such as SolidWorks or CATIA). During the modeling process, the input parameters are generated according to gear design standards (such as GB / T 10095 or ISO 1328) to generate a 3D gear model, including the specific dimensions of the gear tooth profile, rim, and hub. To ensure accuracy, a step-by-step modeling approach is employed. The tooth profile is generated and modified, followed by gear solid creation and the addition of other geometric features. Finally, a 3D geometry model file (e.g., STEP or IGES format) is exported. Material property parameters are used to quantify the strength of the heavy-duty gear material. Based on the collected material performance data, material analysis tools (e.g., ANSYS Material Designer) are used to input material properties such as elastic modulus, yield strength, and density into the simulation software's material library. The accuracy of the input data is verified using a simulation validation program. Based on the 3D geometry model and the quantified material property data, the heavy-duty gear physical structure is digitally modeled. The 3D model is then imported into finite element analysis software (e.g., ABAQUS or ANSYS), where material properties are assigned and meshing is performed. High-quality meshing algorithms (e.g., tetrahedral or hexahedral elements) are used to ensure mesh density and accuracy in key areas of the gear (e.g., tooth roots and addendums). Contact areas, constraints, and loading locations are defined in the model to simulate actual gear operation. After modeling is completed, save the heavy-duty gear physical model as a simulation file format (such as .inp or .cae format) for subsequent mechanical simulation analysis.

[0057] Step S2: dividing each structural geometric unit of the heavy-duty gear according to the heavy-duty gear physical model to generate the structural geometric unit data of the heavy-duty gear;

[0058] In this embodiment of the present invention, structural regions are divided based on a physical model of a heavy-duty gear. The model file is loaded into the simulation software to ensure the correct geometry of the model. Structural regions are divided based on geometric features within the model (such as the tooth root, tooth addendum, tooth flank, and rim). A regional division technique based on mechanical analysis and shape recognition is used to define the stress characteristics and boundary conditions of each region. The tooth root, tooth addendum, tooth flank, and rim regions are partitioned based on their different mechanical properties, distinguishing high-stress and low-stress areas to ensure accurate mechanical analysis. After regional division, the software automatically generates a physical model of the heavy-duty gear for subsequent analysis. Stress-specific analysis of each structural region is performed on the physical model. For high-stress regions such as the tooth root and tooth flank, higher loading intensities are selected, and different torques and loads are applied to the gear's rotating area to simulate real-world operation under heavy load. During the analysis, finite element analysis (FEA) is used to calculate the stress field and determine the stress distribution and deformation in each region. Utilizing stress-specific data for heavy-duty gears within their structural regions, the physical model of the heavy-duty gears is meshed with structural geometry. First, the stress characteristics of the various regions are analyzed based on the stress distribution, particularly in areas of stress concentration. A finer mesh is used for the tooth roots and tooth flanks, where stress is high, to ensure a high density and accuracy of geometric elements in these areas. A coarser mesh is used for low-stress areas to reduce computational effort. The structural geometry data for the heavy-duty gears is generated and saved as a finite element mesh for subsequent stress analysis and simulation.

[0059] Step S3: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the heavy-loaded gear physical model and the geometric unit data of the heavy-loaded gear structure, generating nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation; and performing a mechanical simulation feedback operation of the heavy-loaded gear structure based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation;

[0060] In an embodiment of the present invention, the process of obtaining simulation parameters for heterogeneous operating conditions of construction machinery involves collecting and organizing data on the specific operating environment and operating conditions of the construction machinery. These parameters include, but are not limited to, factors such as load fluctuation, gear speed, mechanical load, and operating temperature. Data acquisition devices and monitoring systems are used to record parameter changes under different operating conditions, specifically, load fluctuation range, gear rotational speed variation patterns, and temperature changes under actual operating conditions. All data is stored as a time series. Analysis tools are used to categorize the changes under different operating conditions and generate operating condition simulation parameters suitable for the physical model of heavy-duty gears. The physical model of heavy-duty gears is analyzed using the simulation parameters for heterogeneous operating conditions of construction machinery. Combined with the obtained operating condition simulation parameters, a mechanical analysis model of the gear under different operating conditions is constructed. The heavy-duty gear physical model and its corresponding operating condition parameters are imported into simulation software, and operating condition simulation is performed using dynamic load simulation methods. Specifically, by applying factors such as load fluctuation, speed variation, and temperature effects, the stress, deformation, and wear of the gear under different operating conditions are simulated. The simulation results output stress field distribution, gear surface wear, and tooth root deformation. The simulation process generates data including load, gear speed, and stress changes during operation. This data provides important insights for subsequent analysis. The simulated operating data for heavy-duty gears is analyzed to extract the stress responses of the gears under different operating conditions. Based on load fluctuations, speed variations, and gear stress characteristics, the operating load fluctuation influence factor, gear speed influence factor, and gear stress influence factor are calculated. The operating load fluctuation influence factor analyzes the extent to which load fluctuations affect gear stress changes. The gear speed influence factor evaluates the dynamic response characteristics of the gear at different speeds. The gear stress influence factor is calculated primarily based on the gear's load capacity and tooth contact characteristics. The gear stress influence factor is calculated based on the ratio of the normal force on the contact surface to the peak stress in the contact area, clarifying stress variations under different operating conditions. These factors are archived in a table to guide nonlinear stress analysis. These factors clarify the stress effects of various operating conditions on gear operation and provide data support for subsequent nonlinear stress analysis. The heavy-duty gear operating stress influence factors are imported and combined with the heavy-duty gear structural geometry data to perform nonlinear stress characteristic analysis. Finite element analysis (FEM) is used to calculate stress distribution for each local element, with a particular focus on areas of high stress concentration. Nonlinear stress response simulations are performed using operating load fluctuation factors, gear speed factors, and gear force factors as inputs. Stress analysis is performed using a nonlinear material model, with the von Mises yield criterion and a bilinear plastic hardening model.The generated local element nonlinear stress characteristic data includes stress peaks, stress gradients, and nonlinear deformation characteristics. These data reveal the operating characteristics of the gear under actual operating conditions, particularly the nonlinear behavior in stress concentration areas, facilitating subsequent design optimization and failure prediction. Simulation parameters for heterogeneous operating conditions (such as load, speed, and temperature) are combined with the corresponding local element nonlinear stress characteristic data for heavy-duty gears to conduct a simulated mechanical analysis of the gear under these heterogeneous operating conditions. Relevant simulation parameters are extracted from various operating conditions of the construction machinery, including those under high loads, high speeds, and harsh environments. These parameters are then input into the heavy-duty gear simulation model. Combined with the previously obtained local element nonlinear stress characteristic data, the finite element method or other mechanical analysis methods are used to calculate the stress distribution, deformation, and potential failure modes of the gear under various operating conditions. The stress response of various gear components under specific operating conditions is primarily calculated, including contact stress and bending stress on the gear tooth surfaces. The generated mechanical data for the heterogeneous gear simulation includes information such as stress distribution, deformation, friction at contact points, and fatigue life estimates. Based on the obtained gear simulation mechanical data of heterogeneous operating conditions, the mechanical simulation feedback operation of the heavy-loaded gear structure is performed, and the mechanical simulation information under the analyzed gear operating conditions is visually fed back to the terminal, so that technicians can understand the corresponding simulated mechanical effects during gear operation.

[0061] Step S4: performing a structural loss trend characteristic analysis of the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation to generate heavy-loaded gear operation structural loss trend characteristic data; performing a structural loss anomaly analysis of the heavy-loaded gear operation based on the structural loss trend characteristic data of the heavy-loaded gear operation to generate heavy-loaded gear structural loss anomaly data;

[0062] In one embodiment of the present invention, nonlinear stress characteristic data of local units of a heavy-loaded gear is acquired during operation. This data details the nonlinear stress variations experienced by each local unit of the gear during operation. Based on this data, a structural loss assessment model based on the energy method or equivalent stress method is used to analyze the stress and strain data of each local unit to assess its energy and structural losses. The loss results for all local units are aggregated to generate structural loss assessment data for the heavy-loaded gear during operation, including the loss amount for each local unit and the overall structural loss trend, providing data support for subsequent loss anomaly analysis. Time series analysis of the nonlinear stress characteristic data is performed to extract the stress variation patterns of each local unit at different time steps. Trend analysis of the nonlinear stress characteristic data is performed using a long short-term memory (LSTM) neural network algorithm. Model training utilizes past data for learning to predict stress variation trends in the gear over future time periods. Through model training and prediction, stress trend data for local units of the heavy-loaded gear during operation is obtained, including the rate of stress variation, fluctuation amplitude, and possible stress concentration trends. This data provides an important basis for subsequent structural loss characteristic and anomaly analysis, accurately predicting gear load variations under different operating conditions. The stress trend data of local units in heavy-duty gear operation is combined with the structural loss assessment data of heavy-duty gear operation. A multi-level regression analysis model is constructed to correlate the stress change trends of local units with the overall structural loss evolution. This analysis focuses on the cumulative effect of stress and the progressive relationship between losses, specifically how the stress changes of local units affect the overall gear structural loss over time. During the model calculation process, through combined analysis of time series data, characteristic data on the structural loss trend of heavy-duty gear operation is generated, including the rate of loss growth, the spatial characteristics of loss distribution, and a prediction model for loss development. In this embodiment of the present invention, characteristic data on the structural loss trend of heavy-duty gear operation is obtained, focusing on anomalies in the loss trend and deviations from the normal pattern. Statistical analysis methods, such as threshold-based anomaly detection algorithms, are used to identify moments within a specific time window when the gear structural loss rate exhibits significant changes. These anomalies typically indicate the risk of excessive wear or damage under certain operating conditions. Based on this, a trend analysis algorithm is used, combined with the specific operating conditions of the gear, to further assess the possible damage location and cause. This generates abnormal structural loss data for heavy-duty gears, including the time and location of the loss anomaly, and its impact on the overall gear life. These abnormal data can provide a basis for subsequent maintenance decisions and timely detect and prevent potential mechanical failures.

[0063] Step S5: performing a heavy-duty gear structural loss disturbance dynamic failure characteristic analysis based on the heavy-duty gear operating structure loss trend characteristic data to generate the heavy-duty gear structural loss disturbance dynamic failure characteristic data; performing a heavy-duty gear structural loss disturbance abnormality analysis based on the heavy-duty gear structural loss disturbance dynamic failure characteristic data to generate the heavy-duty gear structural loss disturbance abnormality data;

[0064] In an embodiment of the present invention, the structural loss trend characteristic data of heavy-duty gear operation is mapped to the simulated working condition data of heavy-duty gear operation to identify the loss disturbance topology data. The specific operation includes matching the structural loss trend characteristic data of heavy-duty gears with the simulated working condition data of engineering machinery to establish a connection between loss disturbance and working condition parameters. During the mapping process, firstly, by analyzing the stress conditions, speed changes and other factors of the gears under different simulated working conditions, it is identified which working conditions have obvious gear loss changes. After the loss disturbance topology data is generated, the loss disturbance of the gear under different operating conditions is located, and data with topological characteristics is generated to help understand the impact of each operating condition on the gear loss. In the process of obtaining historical heavy-duty gear failure operation evaluation data and designing a heavy-duty gear failure operation intelligent evaluation engine based on these data, it is first necessary to collect and organize the historical failure data of heavy-duty gears, and through statistical analysis of these data and using supervised learning algorithms, establish the failure law of gears under different working conditions to form a new model for prediction. The assessment engine combines these historical failure patterns with real-time operating data (such as gear load, speed, and temperature variations) to determine the gear's health status. This system enables real-time assessment of the current gear's failure risk under similar conditions. The assessment engine generates real-time failure risk assessment reports, providing data support for subsequent maintenance and operational decisions. Leveraging heavy-duty gear operating wear disturbance topology data, the engine captures the operational disturbance characteristics of heavy-duty gears due to variations in parameters such as force and speed under different operating conditions. The heavy-duty gear failure operation intelligent assessment engine analyzes the impact of these disturbances on gear performance based on historical failure data and real-time monitoring data. Through dynamic analysis under different operating conditions, it predicts the operational impact of gear degradation patterns (such as increased wear and crack growth). Based on this analysis, the system identifies potential gear failure points under specific operating conditions and provides timely early warnings to prevent failures. Structural wear disturbance anomaly analysis is performed based on the wear disturbance data derived from dynamic failure signature analysis. By monitoring dynamic failure signature data (such as crack growth rate and wear level) in real time, the system determines whether anomalies exist using pre-set thresholds. When a gear loss disturbance corresponding to a specific loss parameter (such as the gear's coefficient of friction or surface wear) causes the gear's operation to exceed a potential safety threshold, the system identifies the anomaly, sets a reasonable threshold range, and evaluates the rationality of the gear's operation based on the impact of the gear loss disturbance, enabling efficient fault detection. For example, if the gear wear rate exceeds a certain range, no gear loss anomaly is detected, but there is a safety hazard to the overall gear operation, the system will flag it as a heavy-duty gear structural loss disturbance anomaly and compare it with historical data to analyze whether the anomaly is caused by external disturbances or internal structural issues.This process is used to identify undetected anomalies in gear wear, but evaluates potential safety anomalies that exist during operation based on historical data to ensure that abnormal characteristics of the gear can be accurately detected.

[0065] Step S6: Perform heavy-loaded gear structure abnormality analysis based on the heavy-loaded gear structure loss abnormality data or the heavy-loaded gear structure loss disturbance abnormality data to generate heavy-loaded gear structure abnormality data; perform heavy-loaded gear structure optimization design feedback operation through the heavy-loaded gear structure abnormality data.

[0066] In an embodiment of the present invention, the nodes corresponding to the abnormal conditions of the gears in the heavy-loaded gear structure loss abnormal data or the heavy-loaded gear structure loss disturbance abnormal data and the corresponding abnormal data are located to obtain the heavy-loaded gear structure abnormal data, and the heavy-loaded gear structure abnormal data is used to perform a heavy-loaded gear structure optimization design feedback operation. The technician receives the heavy-loaded gear structure abnormal data and performs a central optimization design on the heavy-loaded gear structure according to the heavy-loaded gear structure abnormal data, such as replacing materials, improving the gear's anti-loss ability under different working conditions, etc., to reduce potential structural failures and extend the service life of the gear.

[0067] Furthermore, step S1 includes the following steps:

[0068] Step S11: acquiring basic structural parameters of heavy-duty gears of engineering machinery, wherein the basic structural parameters of heavy-duty gears include material characteristic parameters of heavy-duty gears and geometric structure design parameters of heavy-duty gears;

[0069] Step S12: performing three-dimensional modeling of the heavy-duty gear geometric structure according to the heavy-duty gear geometric structure design parameters to generate a three-dimensional model of the heavy-duty gear geometric structure;

[0070] Step S13: performing numerical processing on the strength of the heavy-duty gear material characteristics according to the heavy-duty gear material characteristic parameters to generate numerical heavy-duty gear material characteristic data;

[0071] Step S14: performing digital modeling of the physical structure of the heavy-duty gear using the three-dimensional model of the heavy-duty gear geometric structure and the corresponding digitized heavy-duty gear material characteristic data to generate a heavy-duty gear physical model.

[0072] In an embodiment of the present invention, basic parameters of the heavy-duty gear structure, including material properties and geometric design parameters, are obtained using pre-input engineering machinery design data. Material properties include density, elastic modulus, Poisson's ratio, tensile strength, and yield strength. Mechanical properties are tested on samples using test methods specified in ASTM international standards to obtain numerical material property data. Geometric design parameters include the number of gear teeth, module, tooth width, pressure angle, helix angle, and other parameters. The accuracy and consistency of the parameter sources are ensured by reading design drawings or directly extracting parameter values from computer-aided design (CAD) files. Based on the heavy-duty gear geometric design parameters, 3D modeling of the heavy-duty gear geometry is performed using 3D modeling software (such as SolidWorks or CATIA). During the modeling process, the input parameters are generated according to gear design standards (such as GB / T 10095 or ISO 1328) to generate a 3D gear model, including the specific dimensions of the gear tooth profile, rim, and hub. To ensure accuracy, a step-by-step modeling approach is employed. The tooth profile is generated and modified, followed by gear solid creation and the addition of other geometric features. Finally, a 3D geometry model file (e.g., STEP or IGES format) is exported. Material property parameters are used to quantify the strength of the heavy-duty gear material. Based on the collected material performance data, material analysis tools (e.g., ANSYS Material Designer) are used to input material properties, such as elastic modulus, yield strength, and density, into the simulation software's material library. The accuracy of the input data is verified using a simulation validation program. For example, specimens of the same material are subjected to step-by-step loading, and the yield point is verified to be consistent with experimental data. Finally, the quantified material property data is stored as a material library file (e.g., .mat or .xml format) for subsequent simulation analysis. Based on the 3D geometry model and the quantified material property data, the physical structure of the heavy-duty gear is digitally modeled. The 3D model is then imported into finite element analysis software (e.g., ABAQUS or ANSYS), where material properties are assigned and meshing is performed. Use high-quality meshing algorithms (such as tetrahedral or hexahedral meshing) to ensure mesh density and accuracy in key gear locations, such as the tooth root and tooth addendum. Define contact areas, constraints, and loading locations within the model to simulate the actual gear's operating conditions. Once modeling is complete, save the heavy-duty gear physical model in a simulation file format (such as .inp or .cae) for subsequent mechanical simulation analysis.

[0073] Furthermore, step S2 includes the following steps:

[0074] Step S21: performing a structural area division process on the heavy-duty gear according to the heavy-duty gear physical model to generate a structural area heavy-duty gear physical model;

[0075] Step S22: performing stress-specific analysis on each structural region of the structural region heavy-duty gear physical model to generate stress-specific data of the structural region heavy-duty gear;

[0076] Step S23: using the structural region heavy-duty gear stress-specific data, the structural region heavy-duty gear physical model is divided into various structural geometric units of the heavy-duty gear to generate the heavy-duty gear structural geometric unit data.

[0077] In this embodiment of the present invention, a structural region is divided based on a physical model of a heavy-duty gear. The model file is loaded into the simulation software to ensure the correct geometry of the model. The structural region is divided based on geometric features within the model (such as the tooth root, tooth addendum, tooth flank, and rim). A regional division technique based on mechanical analysis and shape recognition is used to define the stress characteristics and boundary conditions of each region. The tooth root, tooth addendum, tooth flank, and rim regions are partitioned based on their different mechanical properties, distinguishing high-stress and low-stress areas to ensure accurate mechanical analysis. After regional division, the software automatically generates a physical model of the heavy-duty gear for subsequent analysis. The physical model is then subjected to stress-specific analysis of each structural region. For example, a working load is applied to each region, using static and dynamic loading conditions to simulate the actual operating conditions of the gear. For high-stress regions such as the tooth root and tooth flank, higher loading intensities are selected. Different torques and loads are applied to the rotating area of the gear to simulate the actual operation of the gear under heavy load. During the analysis, finite element analysis (FEA) is used to calculate the stress field and determine the stress distribution and deformation in each region. Import the structural area model into the finite element analysis module, for example, select the material properties as follows: elastic modulus E = 2.1 × 10 5MPa, Poisson's ratio ν = 0.3, and yield strength σy = 850 MPa. When applying loads to the model, a torque load M1 = 2000 Nm was applied to the tooth root region, and a linearly distributed load F1 = 1500 N was applied to the tooth flank region. The analysis used a statics solver, dividing the loading conditions into dynamic and static conditions at a speed of n = 1500 rpm. The calculation results showed a maximum equivalent stress σmax = 820 MPa in the tooth root region, a minimum equivalent stress σmin = 400 MPa in the tooth flank region, and a stress concentration factor Kf = 2.5 in the tooth tip region. Based on this data, a stress-specific report for each structural region was generated, clarifying the stress distribution characteristics and trends in each region for subsequent structural optimization and meshing. Using this stress-specific data for heavy-duty gears, the heavy-duty gear physical model was segmented into structural geometric elements. First, the stress characteristics of different regions were analyzed based on the stress distribution, particularly in areas of stress concentration. A finer mesh was used for the root and tooth flank regions with higher stress levels to ensure a high density of geometric elements and higher accuracy. A coarser mesh is used in low-stress areas to reduce computational complexity. For example, in the tooth root region, due to its concentrated and drastic stress variations, a localized mesh refinement strategy is employed, with an element size of 1 mm and C3D10 (tetrahedron quadratic elements) selected as the element type. In the tooth flank region, due to its moderate stress variations, a 2 mm element size is selected, with C3D8R (octahedron simplified elements) used. In the rim region, due to its uniform stress distribution, a 5 mm element size is set, with C3D6 (triangular prism elements) used for simplified modeling. The resulting finite element mesh model contains approximately 1,500,000 elements, of which 65% are in high-stress areas and 35% in low-stress areas. All mesh elements undergo mesh quality testing to ensure mesh deformation is less than 5% and that element shape regularity is met. The generated heavy-duty gear structure geometry is saved in a finite element mesh format for subsequent stress analysis and simulation.

[0078] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S3 in the embodiment, step S3 includes the following steps:

[0079] Step S31: obtaining simulation parameters of heterogeneous operation conditions of construction machinery;

[0080] In an embodiment of the present invention, the process of obtaining simulation parameters for heterogeneous operating conditions of construction machinery includes collecting and organizing data on the specific operating environment and operating conditions of the construction machinery. These parameters include, but are not limited to, factors such as load fluctuation, gear speed, mechanical load, and operating temperature. Data acquisition devices and monitoring systems are used to record parameter changes under different operating conditions, including load fluctuation range, gear rotational speed variation patterns, and temperature changes under actual operating conditions. For example, data acquisition equipment such as strain gauges, thermocouples, and accelerometers are used to record key parameters such as load fluctuation range (e.g., 50-200 kN), gear speed (e.g., 600-1800 rpm), and operating temperature (e.g., -20°C to 80°C). All data is stored in a time series format, and analysis tools are used to categorize changes under different operating conditions to generate operating condition simulation parameters suitable for the heavy-duty gear physical model.

[0081] Step S32: performing heavy-load gear operation simulation analysis on the heavy-load gear physical model using the engineering machinery heterogeneous operation condition simulation parameters to generate heavy-load gear operation simulation condition data;

[0082] In an embodiment of the present invention, the operation simulation working condition analysis of the heavy-duty gear physical model is performed through the heterogeneous operation working condition simulation parameters of the engineering machinery. Combined with the obtained working condition simulation parameters, a mechanical analysis model of the gear under different working conditions is constructed. The heavy-duty gear physical model and its corresponding working condition parameters are imported through the simulation software, and the working condition simulation is performed using a dynamic load simulation method. In particular, by applying factors such as different load fluctuations, speed changes and temperature effects, the stress, deformation and wear of the gear under different operating conditions are simulated. For example, a mechanical analysis model is constructed, in which the gear material is set to Class A alloy steel with a density of ρ=7.8 g / cm 3 , elastic modulus E=2.1×10 5 MPa. Then, different operating parameters are applied, such as a dynamic load F(t)=F+ΔFsin(ωt), where F=100 kN, ΔF=20 kN, ω=2πf, and f is the operating frequency (e.g., 25 Hz). Simultaneously, the linear change in gear speed is simulated as n(t)=n+Δn·t, where n=1000 rpm, Δn=50 rpm / s, and the temperature effect is simulated as T(t)=T+ΔTcos(ωt), where T=25°C, ΔT=10°C. The simulation results output stress field distribution, gear surface wear, and tooth root deformation. The simulation process generates data including load, gear speed, and stress changes during operation, which will provide an important basis for subsequent analysis.

[0083] Step S33: analyzing the heavy-loaded gear operation stress influencing factors based on the heavy-loaded gear operation simulation condition data to generate the heavy-loaded gear operation stress influencing factors, wherein the heavy-loaded gear operation stress influencing factors include the operation load fluctuation influencing factors, the gear speed influencing factors, and the gear force influencing factors;

[0084] In an embodiment of the present invention, simulated operating data of heavy-duty gears is analyzed to extract the stress responses of the gears under different operating conditions. Based on load fluctuations, speed variations, and gear stress characteristics, the operating load fluctuation influence factor, gear speed influence factor, and gear stress influence factor are calculated. The operating load fluctuation influence factor analyzes the degree of influence of load fluctuations on gear stress changes, the gear speed influence factor evaluates the dynamic response characteristics of the gear at different speeds, and the gear stress influence factor is calculated primarily based on the gear's load capacity and tooth contact characteristics. For example, a multivariate analysis of load fluctuations, speed variations, and gear stress characteristics is performed to calculate the stress influence factor. The load fluctuation influence factor is calculated as the stress fluctuation amplitude divided by the average stress value. For example, when the maximum stress fluctuation in the tooth root region is 150 MPa and the average stress is 600 MPa, the load fluctuation influence factor is 0.25. The speed influence factor is obtained by analyzing the stress change rate of the gear at different speeds. For example, if the speed increases by 500 rpm and the stress changes by 20 MPa, the speed influence factor is 0.04 MPa / rpm. Gear stress influencing factors are calculated based on the ratio of the normal force on the contact surface to the peak stress in the contact area, clarifying the stress variations under different operating conditions. These factors are documented in a table format to guide nonlinear stress analysis. These factors clearly define the stress effects of various operating conditions on gear operation and provide data support for further nonlinear stress analysis.

[0085] Step S34: performing a nonlinear stress characteristic analysis of a local unit of heavy-loaded gear operation according to the stress influencing factor of the heavy-loaded gear operation and the geometric unit data of the heavy-loaded gear structure, and generating nonlinear stress characteristic data of the local unit of heavy-loaded gear operation.

[0086] In this embodiment of the present invention, nonlinear stress characteristic analysis is performed by importing operational stress factors for heavy-duty gears and combining them with geometric unit data for the heavy-duty gear structure. Finite element analysis (FEM) is used to calculate stress distribution for each local element, with a particular focus on areas of high stress concentration. The operational load fluctuation factor, gear speed factor, and gear force factor are used as inputs to simulate the nonlinear stress response. For example, a refined mesh with a 1 mm cell size is used for high-stress areas such as the tooth root. The load fluctuation factor and speed factor are applied during the analysis. The stress analysis is performed by setting a nonlinear material model with the von Mises yield criterion and a bilinear plastic hardening model (initial hardening modulus of 800 MPa and subsequent hardening modulus of 400 MPa). The analysis results show that the maximum stress in the tooth root region is concentrated at a radius of 6 mm, with a peak stress of 750 MPa and a nonlinear deformation increment of 0.02 mm. The generated local element nonlinear stress characteristic data, including stress peaks, stress gradients, and nonlinear deformation characteristics, will reveal the operational characteristics of the gear under actual operating conditions, particularly the nonlinear behavior in stress concentration areas, facilitating subsequent design optimization and failure prediction.

[0087] Step S35: Perform gear simulation mechanical analysis of heterogeneous operating conditions based on the nonlinear stress characteristic data of the local unit of heavy-duty gear operation corresponding to the simulation parameters of the heterogeneous operating conditions of the engineering machinery, and generate gear simulation mechanical data of the heterogeneous operating conditions; perform mechanical simulation feedback operations of the heavy-duty gear structure through the gear simulation mechanical data of the heterogeneous operating conditions.

[0088] In this embodiment of the present invention, simulation parameters for heterogeneous operating conditions of construction machinery (such as load, speed, and temperature) are combined with the corresponding nonlinear stress characteristic data of local units of heavy-duty gears to perform a simulated mechanical analysis of the gears under these conditions. Relevant simulation parameters are extracted from the various operating conditions of the construction machinery, including those under high load, high speed, and harsh environments. These parameters are input into the heavy-duty gear simulation model. Combined with the previously acquired nonlinear stress characteristic data of local units, the finite element method or other mechanical analysis methods are used to calculate the stress distribution, deformation, and possible failure modes of the gears under different operating conditions. The stress response of various parts of the gear under specific operating conditions is primarily calculated, including contact stress and bending stress on the gear tooth surfaces. The generated mechanical data for the heterogeneous gear simulation includes information such as the gear stress distribution, deformation, friction at contact points, and fatigue life estimates. Based on this obtained mechanical data for the heterogeneous gear simulation, a mechanical simulation feedback process for the heavy-duty gear structure is performed. The analyzed mechanical simulation information for the gear operating conditions is visualized and fed back to a terminal, allowing technicians to understand the corresponding simulated mechanical effects of the gear operation.

[0089] Furthermore, step S34 includes the following steps:

[0090] Step S341: performing an analysis of the correlation characteristics between the operating load and the gear speed based on the operating load fluctuation influencing factor and the gear speed influencing factor, and generating operating load-gear speed correlation characteristic data;

[0091] Step S342: performing a heavy-duty gear simulated force numerical transmission benefit analysis on the gear force influencing factors based on the operating load-gear speed correlation characteristic data, and generating heavy-duty gear simulated force numerical transmission benefit data;

[0092] Step S343: performing a heavy-duty gear structure geometric unit spatial feature analysis based on the heavy-duty gear structure geometric unit data to generate heavy-duty gear structure geometric unit spatial feature data;

[0093] Step S344: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the numerical transmission benefit data of the simulated force of the heavy-loaded gear and the spatial characteristic data of the geometric unit of the heavy-loaded gear structure, and generating the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation.

[0094] In an embodiment of the present invention, numerical data on factors influencing operational load fluctuations and gear speed are collected. This data is derived from load and speed data under different operating conditions, including the load fluctuation range and speed variation patterns of heavy-duty machinery. The relationship between operational load fluctuations and gear speed is quantitatively analyzed using correlation analysis methods, particularly multiple regression analysis or correlation coefficient calculation. During the analysis, characteristic data related to operational load and gear speed correlation is generated, combining the response characteristics of gear speed to load fluctuations under different operating conditions. This data, including a mathematical model or functional form of the relationship between load and speed variations, can clarify the influence relationship between the two and provide the necessary data support for subsequent force transmission analysis. A numerical transmission benefit analysis method is used to establish a force numerical transmission benefit analysis model based on the mechanical behavior of the gear and the mechanical input and output values. The load and speed correlation characteristic data are input into the force numerical transmission benefit analysis model, taking into account the impact of load and speed variations on gear forces under different operating conditions. Through numerical calculations, a mathematical model of gear force transmission is established, incorporating the gear's geometric structure, material properties, and dynamic response characteristics. During the calculation process, a numerical transfer efficiency analysis method was used to simulate the load transmission path and efficiency of gear force fluctuations due to load fluctuations and speed variations. For example, for a load fluctuation range of 50-150 kN, a speed variation of 600-1200 rpm, a material elastic modulus E = 2.1×10^5 MPa, and a Poisson's ratio ν = 0.3, simulation software was used to calculate the load efficiency (e.g., 85%-92%) and stress concentration factor (e.g., 1.8-2.2) along the transmission path, as well as their impact on gear force. Ultimately, numerical transfer efficiency data for simulated heavy-duty gear force was generated, including load transfer efficiency, stress concentration, and their impact on gear load capacity. This facilitates the evaluation of gear force efficiency under different operating conditions. Spatial characteristic analysis of the heavy-duty gear structural geometric unit data was performed. This data, which details the size, shape, and spatial distribution of each gear geometric unit, was used. For example, spatial characteristic analysis methods were used to analyze the spatial relationships and structural characteristics of the gear geometric units, including the contact surfaces, contact angles, and spatial positions of each unit. Computational geometry methods, such as principal component analysis or structural symmetry analysis, are used to calculate the contact area (e.g., 80 mm²) and contact angle (e.g., 20°) of the contact surface to extract spatial characteristic data from the gear structure. Structural symmetry analysis is then used to identify the symmetry axes and key element locations of the gear model. This data provides geometric support for subsequent nonlinear stress analysis, ensuring consistency between the actual gear structure and the simulation model. Spatial characteristic data for geometric elements is generated, including the geometric relationships of various gear components, contact surface characteristics, and local shape properties, providing accurate geometric support for stress analysis. Numerical transfer efficiency data for simulated heavy-duty gears, as well as spatial characteristic data for the geometric elements of the heavy-duty gear structure, are input.Incorporating finite element analysis methods, nonlinear stress analysis of local elements of the gear structure is performed, focusing specifically on stress concentration areas such as tooth contact and transition regions. During the analysis, the nonlinear effects of load fluctuations, speed changes, and the gear structure's geometry are considered, and the stress distribution, strain distribution, and deformation of each local element are calculated by solving a set of nonlinear equations. The generated nonlinear stress characteristic data includes the maximum stress value, stress gradient, deformation, and nonlinear stress response curve of the local element. This data effectively describes the operating characteristics of the gear under actual working conditions, especially its performance in high-stress areas, providing a key basis for gear performance optimization and failure prediction.

[0095] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S4 in the embodiment, step S4 includes the following steps:

[0096] Step S41: performing a structural loss assessment process for the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation to generate structural loss assessment data for the heavy-loaded gear operation;

[0097] In an embodiment of the present invention, nonlinear stress characteristic data of local units of heavy-duty gear operation are obtained. These data describe in detail the nonlinear stress changes to which each local unit of the gear is subjected during operation. On this basis, a structural loss assessment model based on the energy method or the equivalent stress method is used for processing, and the stress and strain data of each local unit are analyzed to evaluate the energy loss and structural loss of each local unit. For example, the stress peak of a certain unit is 450 MPa, and the strain is 0.002. The stress of each local unit is numerically integrated, and its energy loss during the working cycle is calculated to be 1.2 J. Further combined with the fatigue properties of the material (such as yield strength of 350 MPa), the structural loss data of the local unit is derived. The loss results of all local units are summarized to generate structural loss assessment data for heavy-duty gear operation, including the loss amount of each local unit and the overall structural loss trend, to provide data support for subsequent loss anomaly analysis.

[0098] Step S42: performing a stress trend analysis of the local unit of the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation, and generating stress trend data of the local unit of the heavy-loaded gear operation;

[0099] In this embodiment of the present invention, time series analysis is performed on nonlinear stress characteristic data to extract the stress variation patterns of each local unit at different time steps. Trend analysis of the nonlinear stress characteristic data is performed using a long short-term memory (LSTM) neural network algorithm. Model training utilizes past data to predict stress variation trends in gears over future time periods. Through model training and prediction, trend data on local unit stresses in heavily loaded gears is obtained, including the rate of stress variation, fluctuation amplitude, and possible stress concentration trends. This data provides an important basis for subsequent structural loss characteristic analysis and anomaly analysis, accurately predicting gear load variations under different operating conditions.

[0100] Step S43: performing a structural loss trend characteristic analysis of the heavy-loaded gear operation on the heavy-loaded gear operation structural loss assessment data based on the heavy-loaded gear operation local unit stress trend data, and generating heavy-loaded gear operation structural loss trend characteristic data;

[0101] In an embodiment of the present invention, the stress trend data of the local unit of the heavy-duty gear operation is combined with the evaluation data of the structural loss of the heavy-duty gear operation. By constructing a multi-level regression analysis model, the stress change trend of the local unit is correlated with the loss evolution of the overall structure. In this analysis process, the focus is on the progressive relationship between the stress accumulation effect and the loss, that is, how the stress change of the local unit will affect the structural loss of the entire gear over time. In the model calculation process, through the combined analysis of time series data, the characteristic data of the heavy-duty gear operation structure loss trend are generated, including the rate of loss growth, the spatial characteristics of loss distribution, and the prediction model of loss development.

[0102] Step S44: performing heavy-loaded gear structural loss anomaly analysis based on the heavy-loaded gear operation structural loss trend characteristic data to generate heavy-loaded gear structural loss anomaly data.

[0103] In an embodiment of the present invention, characteristic data of the loss trend of the operating structure of heavy-duty gears is obtained, focusing on abnormal points in the loss trend and parts that deviate from the normal pattern. Through statistical analysis methods, such as a threshold-based anomaly detection algorithm, the moments when the gear structure loss rate changes significantly within a certain time window are identified. These anomalies usually indicate that the gear may be at risk of excessive wear or damage under certain operating conditions. On this basis, a trend analysis algorithm is used, combined with the specific operating conditions of the gear, to further evaluate the possible damage location and cause. Ultimately, abnormal loss data of the heavy-duty gear structure is generated, including the time and location of the loss anomaly and its impact on the overall gear life. These abnormal data can provide a basis for subsequent maintenance decisions, and timely detect and prevent potential mechanical failures.

[0104] Furthermore, step S42 includes the following steps:

[0105] The time series data analysis of the local unit nonlinear stress characteristic data of the heavy-loaded gear operation is performed to generate the time series local unit nonlinear stress characteristic data; the local unit stress trend analysis of the heavy-loaded gear operation is performed on the time series local unit nonlinear stress characteristic data using the preset long short-term memory neural network algorithm to generate the local unit stress trend data of the heavy-loaded gear operation.

[0106] In one embodiment of the present invention, time-series data analysis is performed on the nonlinear stress characteristic data of local units in heavy-duty gear operation. This nonlinear stress characteristic data is derived from stress measurement data of each local unit of the gear. This data is collected in real time by sensors and reflects the nonlinear stress response characteristics of each local unit under different operating conditions. The stress data for each local unit is first arranged in chronological order to generate a stress data series containing a time dimension. A sliding average method is then used to denoise the raw stress data to eliminate random fluctuations and retain the main trend information of stress changes, thereby obtaining the time-series nonlinear stress characteristic data of the local units. This time-series data is then analyzed using a long short-term memory (LSTM) neural network. The LSTM model, through its unique memory mechanism, learns the long-term dependencies of time series data, thereby capturing the trend changes in stress data. During the analysis process, the data is first normalized to the range [0, 1] to meet the input requirements of the LSTM model. The LSTM model is then trained and validated. For example, the stress data for a unit over five time steps is [400, 420, 450, 480, 500] MPa. A stress trend prediction model was constructed using an LSTM neural network. The input layer contained time step data, the hidden layer consisted of 64 neurons, and the activation function was Reinforced Luminance (ReLU). Mean squared error (MSE) was used as the loss function during training, and convergence was achieved after 50 iterations, predicting the next stress value to be 530 MPa. The model generated stress trend data, including stress growth rate (e.g., 10 MPa / step) and fluctuation amplitude (e.g., ±15 MPa). Finally, the model output predicted local unit stress values for future time periods, generating local unit stress trend data for heavy-duty gear operation. This data, including future stress trends, stress fluctuation amplitudes, and possible areas of stress concentration, provides important information for subsequent structural loss assessment and anomaly analysis.

[0107] Furthermore, step S43 includes the following steps:

[0108] Based on the local unit stress trend data of heavy-loaded gear operation, the heavy-loaded gear operation structural loss assessment data is recursively analyzed to generate recursive heavy-loaded gear operation structural loss data; based on the recursive heavy-loaded gear operation structural loss data, the structural loss trend characteristic analysis of heavy-loaded gear operation is performed to generate heavy-loaded gear operation structural loss trend characteristic data.

[0109] In an embodiment of the present invention, local unit stress trend data is input into a recursive analysis model to capture the long-term impact of stress changes on structural losses. Recursive analysis predicts future changes in structural losses by considering the relationship between the stress value at the current moment and the losses at the previous moment. This analysis uses a recursive algorithm (such as the recursive least squares method) to weight the stress trend data of each local unit to generate recursive heavy-duty gear operating structural loss data. This data reflects the cumulative losses of each local unit of the heavy-duty gear at different operating stages and can reveal potential structural damage caused by different stress loads. Recursive heavy-duty gear operating structural loss data is processed using regression analysis. A mathematical model for the variation of losses over time is established, and a curve fit is obtained. For example, a polynomial regression model is used, with the model expression: W = a·t^2+b·t+c, where t is the time step and a, b, and c are regression coefficients. By performing regression analysis on the recursive loss data, a prediction model for the variation of losses over time is obtained. Assuming the regression analysis results are a=0.02, b=0.1, and c=0.0, the model can be used to predict the wear trend of gears over long periods of operation. By extracting trend features from the recursive loss data, including the rate of loss growth and spatial distribution characteristics, the wear pattern of heavy-duty gears over long periods of operation is determined. This analysis focuses on the gradual accumulation of fatigue damage, wear, and other phenomena in gears. The generation of structural loss trend characteristic data reflects the degree of wear of each local unit at each stage, as well as the damage trend of the overall gear structure, providing data support for subsequent structural optimization and maintenance decisions.

[0110] Furthermore, step S5 includes the following steps:

[0111] Step S51: mapping the heavy-loaded gear operation structure loss trend characteristic data to the heavy-loaded gear operation simulation condition data to perform loss disturbance topology data identification, and generate heavy-loaded gear operation loss disturbance topology data;

[0112] Step S52: Acquire historical heavy-duty gear failure operation evaluation data, and design a heavy-duty gear failure operation intelligent evaluation engine based on the historical heavy-duty gear failure operation evaluation data;

[0113] Step S53: performing a heavy-duty gear failure characteristic analysis on the heavy-duty gear operation loss disturbance topology data by using the heavy-duty gear failure operation intelligent evaluation engine to generate the heavy-duty gear failure characteristic data.

[0114] Step S54: performing heavy-loaded gear structure loss disturbance anomaly analysis based on the loss disturbance heavy-loaded gear dynamic failure characteristic data to generate heavy-loaded gear structure loss disturbance anomaly data.

[0115] In one embodiment of the present invention, heavy-duty gear operating structural loss trend characteristic data is mapped to simulated operating condition data for heavy-duty gear operation to identify loss disturbance topology data. Specifically, this involves matching the heavy-duty gear structural loss trend characteristic data with simulated operating condition data for engineering machinery to establish a relationship between loss disturbances and operating condition parameters. During the mapping process, factors such as the gear stress and speed variations under different simulated operating conditions are analyzed to identify operating conditions where significant gear loss variations occur. Once the loss disturbance topology data is generated, the gear loss disturbances under different operating conditions are located, and data with topological characteristics is generated to help understand the impact of each operating condition on gear loss. To obtain historical heavy-duty gear failure operation assessment data and design an intelligent heavy-duty gear failure operation assessment engine based on this data, historical failure data for heavy-duty gears must first be collected and organized, including failure modes (such as gear wear, tooth breakage, and fatigue cracks) and gear loss growth rates. For example, gear wear, gear cracks, and gear fractures account for 60%, 30%, and 10% of historical failures, respectively. By statistically analyzing this data and utilizing supervised learning algorithms, the failure patterns of gears under different operating conditions are established, forming a new predictive model. The assessment engine combines these historical failure patterns with real-time operating data (such as gear load, speed, and temperature fluctuations) to determine the health of the gears. When designing the intelligent assessment engine, machine learning or statistical regression algorithms are used to model historical data, resulting in a system that can assess the failure risk of current gears under similar conditions in real time. Ultimately, the assessment engine generates real-time failure risk assessment reports, providing data support for subsequent maintenance and operational decisions. The heavy-duty gear operating failure disturbance topology data captures the disturbance characteristics of heavy-duty gear operation caused by variations in gear load, speed, and other parameters under different operating conditions. The heavy-duty gear failure operation intelligent assessment engine analyzes the impact of these disturbances on gear performance based on historical failure data and real-time monitoring data. For example, when a gear experiences large load fluctuations under certain operating conditions, this can lead to material fatigue, crack growth, or excessive wear. Through dynamic analysis under different operating conditions, the operational impact of these gear degradation patterns (such as increased wear and crack growth) is predicted. Based on this analysis, the system can identify potential failure points of gears under specific operating conditions and provide timely warnings through early warning to prevent failures. Structural loss disturbance anomaly analysis is performed based on the loss disturbance data derived from dynamic failure signature analysis. Dynamic failure signature data (such as crack propagation rate and wear level) is monitored in real time, and set thresholds are used to determine whether anomalies exist. When the gear operating loss disturbance corresponding to a certain loss parameter (such as the gear's friction coefficient or surface wear) causes the gear operation to exceed the potential safety threshold, the system identifies the anomaly, sets a reasonable threshold range, and evaluates the rationality of the gear operation based on the impact of the gear loss disturbance, thereby achieving efficient fault detection.For example, when the gear wear rate exceeds a certain range, even though no abnormal gear loss is detected, there is a safety risk to the overall gear operation. This is then flagged as a heavy-duty gear structural loss disturbance anomaly, and compared with historical data to analyze whether the anomaly is caused by external disturbances or internal structural issues. This process is used to identify undetected anomalies in gear loss, but evaluates their potential safety anomalies during operation based on historical data to ensure accurate detection of abnormal gear characteristics.

[0116] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0117] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A mechanical simulation analysis method for a heavy-duty gear structure, characterized in that: The following steps are involved: Step S1: Obtaining basic parameters of heavy-duty gear structures of engineering machinery; Perform digital modeling of the heavy-duty gear physical structure based on the basic structural parameters of the heavy-duty gear to generate a heavy-duty gear physical model; Step S2: dividing each structural geometric unit of the heavy-duty gear according to the heavy-duty gear physical model to generate the structural geometric unit data of the heavy-duty gear; Step S3: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the heavy-loaded gear physical model and the heavy-loaded gear structure geometric unit data, and generating nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation; Perform mechanical simulation feedback on heavy-loaded gear structures based on the nonlinear stress characteristic data of local elements of heavy-loaded gears; Step S4: performing structural loss trend characteristic analysis of heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of heavy-loaded gear operation, and generating structural loss trend characteristic data of heavy-loaded gear operation; According to the heavy-loaded gear operation structure loss trend characteristic data, the heavy-loaded gear structure loss abnormality analysis is carried out to generate the heavy-loaded gear structure loss abnormality data; Step S5: performing a dynamic failure characteristic analysis of heavy-duty gears with loss disturbance based on the loss trend characteristic data of the heavy-duty gear operation structure, and generating dynamic failure characteristic data of heavy-duty gears with loss disturbance; Based on the loss disturbance heavy-loaded gear dynamic failure characteristic data, the heavy-loaded gear structure loss disturbance anomaly analysis is performed to generate the heavy-loaded gear structure loss disturbance anomaly data; Step S6: performing heavy-loaded gear structure abnormality analysis based on the heavy-loaded gear structure loss abnormality data or the heavy-loaded gear structure loss disturbance abnormality data to generate heavy-loaded gear structure abnormality data; Execute feedback on the optimized design of heavy-duty gear structures through abnormal data of heavy-duty gear structures.

2. The mechanical simulation analysis method for heavy-duty gear structure according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: acquiring basic structural parameters of heavy-duty gears of engineering machinery, wherein the basic structural parameters of heavy-duty gears include material characteristic parameters of heavy-duty gears and geometric structure design parameters of heavy-duty gears; Step S12: performing three-dimensional modeling of the heavy-duty gear geometric structure according to the heavy-duty gear geometric structure design parameters to generate a three-dimensional model of the heavy-duty gear geometric structure; Step S13: performing numerical processing on the strength of the heavy-duty gear material characteristics according to the heavy-duty gear material characteristic parameters to generate numerical heavy-duty gear material characteristic data; Step S14: performing digital modeling of the physical structure of the heavy-duty gear using the three-dimensional model of the heavy-duty gear geometric structure and the corresponding digitized heavy-duty gear material characteristic data to generate a heavy-duty gear physical model.

3. The mechanical simulation analysis method for heavy-duty gear structure according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing a structural area division process on the heavy-duty gear according to the heavy-duty gear physical model to generate a structural area heavy-duty gear physical model; Step S22: performing stress-specific analysis on each structural region of the structural region heavy-duty gear physical model to generate stress-specific data of the structural region heavy-duty gear; Step S23: using the structural region heavy-duty gear stress-specific data, the structural region heavy-duty gear physical model is divided into various structural geometric units of the heavy-duty gear to generate the heavy-duty gear structural geometric unit data.

4. The mechanical simulation analysis method for heavy-duty gear structure according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: obtaining simulation parameters of heterogeneous operation conditions of construction machinery; Step S32: performing heavy-load gear operation simulation analysis on the heavy-load gear physical model using the engineering machinery heterogeneous operation condition simulation parameters to generate heavy-load gear operation simulation condition data; Step S33: analyzing the heavy-loaded gear operation stress influencing factors based on the heavy-loaded gear operation simulation condition data to generate the heavy-loaded gear operation stress influencing factors, wherein the heavy-loaded gear operation stress influencing factors include the operation load fluctuation influencing factors, the gear speed influencing factors, and the gear force influencing factors; Step S34: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the stress influencing factor of the heavy-loaded gear operation and the geometric unit data of the heavy-loaded gear structure, and generating nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation; Step S35: Perform gear simulation mechanical analysis of heterogeneous operating conditions based on the nonlinear stress characteristic data of the local unit of heavy-duty gear operation corresponding to the simulation parameters of the heterogeneous operating conditions of the engineering machinery, and generate gear simulation mechanical data of the heterogeneous operating conditions; perform mechanical simulation feedback operations of the heavy-duty gear structure through the gear simulation mechanical data of the heterogeneous operating conditions.

5. The mechanical simulation analysis method for heavy-duty gear structure according to claim 4, characterized in that: Step S34 includes the following steps: Step S341: performing an analysis of the correlation characteristics between the operating load and the gear speed based on the operating load fluctuation influencing factor and the gear speed influencing factor, and generating operating load-gear speed correlation characteristic data; Step S342: performing a heavy-duty gear simulated force numerical transmission benefit analysis on the gear force influencing factors based on the operating load-gear speed correlation characteristic data, and generating heavy-duty gear simulated force numerical transmission benefit data; Step S343: performing a heavy-duty gear structure geometric unit spatial feature analysis based on the heavy-duty gear structure geometric unit data to generate heavy-duty gear structure geometric unit spatial feature data; Step S344: performing a nonlinear stress characteristic analysis of a local unit of the heavy-loaded gear operation based on the numerical transmission benefit data of the simulated force of the heavy-loaded gear and the spatial characteristic data of the geometric unit of the heavy-loaded gear structure, and generating the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation.

6. The mechanical simulation analysis method for heavy-duty gear structure according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing a structural loss assessment process for the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation to generate structural loss assessment data for the heavy-loaded gear operation; Step S42: performing a stress trend analysis of the local unit of the heavy-loaded gear operation based on the nonlinear stress characteristic data of the local unit of the heavy-loaded gear operation, and generating stress trend data of the local unit of the heavy-loaded gear operation; Step S43: performing a structural loss trend characteristic analysis of the heavy-loaded gear operation on the heavy-loaded gear operation structural loss assessment data based on the heavy-loaded gear operation local unit stress trend data, and generating heavy-loaded gear operation structural loss trend characteristic data; Step S44: performing heavy-loaded gear structural loss anomaly analysis based on the heavy-loaded gear operation structural loss trend characteristic data to generate heavy-loaded gear structural loss anomaly data.

7. The mechanical simulation analysis method for heavy-duty gear structure according to claim 6, characterized in that: Step S42 includes the following steps: The time series data analysis of the local unit nonlinear stress characteristic data of the heavy-loaded gear operation is performed to generate the time series local unit nonlinear stress characteristic data; the local unit stress trend analysis of the heavy-loaded gear operation is performed on the time series local unit nonlinear stress characteristic data using the preset long short-term memory neural network algorithm to generate the local unit stress trend data of the heavy-loaded gear operation.

8. The mechanical simulation analysis method for heavy-duty gear structure according to claim 6, characterized in that: Step S43 includes the following steps: Based on the local unit stress trend data of heavy-loaded gear operation, the heavy-loaded gear operation structural loss assessment data is recursively analyzed to generate recursive heavy-loaded gear operation structural loss data; based on the recursive heavy-loaded gear operation structural loss data, the structural loss trend characteristic analysis of heavy-loaded gear operation is performed to generate heavy-loaded gear operation structural loss trend characteristic data.

9. The mechanical simulation analysis method for heavy-duty gear structure according to claim 4, characterized in that: Step S5 includes the following steps: Step S51: mapping the heavy-loaded gear operation structure loss trend characteristic data to the heavy-loaded gear operation simulation condition data to perform loss disturbance topology data identification, and generate heavy-loaded gear operation loss disturbance topology data; Step S52: Acquire historical heavy-duty gear failure operation evaluation data, and design a heavy-duty gear failure operation intelligent evaluation engine based on the historical heavy-duty gear failure operation evaluation data; Step S53: performing a heavy-duty gear failure characteristic analysis on the heavy-duty gear operation loss disturbance topology data by using the heavy-duty gear failure operation intelligent evaluation engine to generate the heavy-duty gear failure characteristic data. Step S54: performing heavy-loaded gear structure loss disturbance anomaly analysis based on the loss disturbance heavy-loaded gear dynamic failure characteristic data to generate heavy-loaded gear structure loss disturbance anomaly data.

Images